---
title: "Discussion on \"GRUs are lit 🔥 But why so little traction?\" | Hashnode"
description: "Discussion on \"GRUs are lit 🔥 But why so little traction?\". LSTMs are popular because it solved the problem of vanishing gradient with RNNs. But so do Gated Recurrent Units (GRUs). On top of it, GRUs also have less parameters to learn compared to LSTM. And yet, GRUs are not used as much in the industry as LST..."
url: "https://hashnode.com/posts/grus-are-lit-but-why-so-little-traction/65a8e896d364e6f2f60b7cdf"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [GRUs are lit 🔥 But why so little traction?](https://japkeeratsingh.com/grus-are-lit-but-why-so-little-traction?utm_source=hashnode&utm_medium=feed)

LSTMs are popular because it solved the problem of vanishing gradient with RNNs. But so do Gated Recurrent Units (GRUs). On top of it, GRUs also have less parameters to learn compared to LSTM. And yet, GRUs are not used as much in the industry as LST...

Jan 18, 2024 · 3 min read · japkeeratsingh.com  
Read the article

-   [#gated-recurrent-unit](https://hashnode.com/tag/gated-recurrent-unit)
-   [#nlp](https://hashnode.com/tag/nlp)
-   [#natural-language-processing](https://hashnode.com/tag/natural-language-processing)
-   [#deep-learning](https://hashnode.com/tag/deep-learning)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#gru](https://hashnode.com/tag/gru)
-   [#rnn](https://hashnode.com/tag/rnn)

## Written by

[Japkeerat Singh](https://hashnode.com/@japkeerat)

@japkeerat · Toronto, CA

  
[View profile](https://hashnode.com/@japkeerat)

I help companies make $$$ by developing AI-centric Products // Book a call with me @ japkeeratsingh.com/call

Hi, I am Japkeerat. I am working as a Machine Learning Engineer since January 2020, straight out of college. During this period, I've worked on extremely challenging projects - Security Vulnerability Detection using Graph Neural Networks, User Segmentation for better click through rate of notifications, and MLOps Infrastructure development for startups, to name a few. I keep my articles precise, maximum of 4 minutes of reading time. I'm currently actively writing 2 series - one for beginners in Machine Learning and another related to more advance concepts. The newsletter, if you subscribe to, will send 1 article every Thursday on the advance concepts.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
